SWE-Bench Pro

Name: SWE-Bench Pro — AI Model Benchmark Results
Creator: Neura Market

Harder subset of SWE-Bench with more complex multi-file changes.

coding0-100 percent

Model Rankings (55)

#	Model	Score	Provider	Source
	Claude Fable 5🇺🇸			verified
	Claude Mythos Preview🇺🇸			verified
	Claude Opus 4.8🇺🇸			verified
	Q Qwen3.8 Max🇨🇳			verified
	T Hy4 preview🇨🇳			verified
	X Grok 4.5🇺🇸			verified
	GPT-5.6 Sol🇺🇸			verified
	Claude Opus 4.7🇺🇸			verified
	GPT-5.6 Terra🇺🇸			verified
	Claude Sonnet 5🇺🇸			verified
	GPT-5.6 Luna🇺🇸			verified
	Q Qwen3.8-Flash-Next🇨🇳			verified
	Q Qwen3.8 Flash🇨🇳			verified
	Z GLM-5.2🇨🇳			verified
	Q Qwen3.8-27B🇨🇳			verified
	M Muse Spark 1.1🇺🇸			verified
	Q Qwen3.7 Max🇨🇳			verified
	P Laguna S 2.1🇺🇸			verified
	MiniMax M3🇨🇳			verified
	Gemini 3.6 Flash🇺🇸			verified
	M Kimi K2.6🇨🇳			verified
	GPT-5.5🇺🇸			verified
	Z GLM-5.1🇨🇳			verified
	T Hy3🇨🇳			verified
	GPT-5.4🇺🇸			verified
	Q Qwen3.7-Plus🇨🇳			verified
	B Seed 2.1 Pro🇨🇳			verified
	X MiMo-V2.5-Pro🇨🇳			verified
	B Seed 2.1 Turbo🇨🇳			verified
	GPT-5.3 Codex🇺🇸			verified
	Q Qwen3.6 Plus🇨🇳			verified
	GPT-5.2 Codex🇺🇸			verified
	MiniMax M2.7🇨🇳			verified
	X MiMo-V2.5🇨🇳			verified
	T Inkling-Small🇺🇸			verified
	DeepSeek-V4-Pro-Max🇨🇳			verified
	MiniMax M2.5🇨🇳			verified
	Gemini 3.5 Flash🇺🇸			verified
	GPT-5.4 mini🇺🇸			verified
	Gemini 3.5 Flash-Lite🇺🇸			verified
	Gemini 3.1 Pro🇺🇸			verified
	Q Qwen3.6-27B🇨🇳			verified
	MAI-Thinking-1🇺🇸			verified
	DeepSeek-V4-Flash-Max🇨🇳			verified
	M Muse Spark🇺🇸			verified
	GPT-5.4 nano🇺🇸			verified
	DeepSeek-V4-Flash-0423🇨🇳			verified
	M Muse Glimmer-30B🇺🇸			verified
	MAI-Code-1-Flash🇺🇸			verified
	M Kimi K2.5🇨🇳			verified
	Q Qwen3.6-35B-A3B🇨🇳			verified
	P Laguna XS 2.1🇺🇸			verified
	North Mini Code 1.0🇨🇦			verified
	I IBM Granite 4.2 30B🇺🇸			verified
	I IBM Granite 4.2 8B🇺🇸			verified

AI Model Benchmarks

SWE-Bench Pro

Model Rankings (55)